last-checkpoint/trainer_state.json

{
  "best_metric": 1.4968665838241577,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.02577873254564984,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008592910848549946,
      "eval_loss": 1.6741554737091064,
      "eval_runtime": 34.376,
      "eval_samples_per_second": 14.254,
      "eval_steps_per_second": 7.127,
      "step": 1
    },
    {
      "epoch": 0.0025778732545649837,
      "grad_norm": 0.15027430653572083,
      "learning_rate": 3e-05,
      "loss": 1.6471,
      "step": 3
    },
    {
      "epoch": 0.004296455424274973,
      "eval_loss": 1.6712243556976318,
      "eval_runtime": 34.1646,
      "eval_samples_per_second": 14.342,
      "eval_steps_per_second": 7.171,
      "step": 5
    },
    {
      "epoch": 0.0051557465091299675,
      "grad_norm": 0.15287861227989197,
      "learning_rate": 6e-05,
      "loss": 1.7026,
      "step": 6
    },
    {
      "epoch": 0.007733619763694952,
      "grad_norm": 0.17870335280895233,
      "learning_rate": 9e-05,
      "loss": 1.6398,
      "step": 9
    },
    {
      "epoch": 0.008592910848549946,
      "eval_loss": 1.6417946815490723,
      "eval_runtime": 34.2263,
      "eval_samples_per_second": 14.316,
      "eval_steps_per_second": 7.158,
      "step": 10
    },
    {
      "epoch": 0.010311493018259935,
      "grad_norm": 0.1880308836698532,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.6545,
      "step": 12
    },
    {
      "epoch": 0.01288936627282492,
      "grad_norm": 0.1989935040473938,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5914,
      "step": 15
    },
    {
      "epoch": 0.01288936627282492,
      "eval_loss": 1.5794165134429932,
      "eval_runtime": 34.32,
      "eval_samples_per_second": 14.277,
      "eval_steps_per_second": 7.139,
      "step": 15
    },
    {
      "epoch": 0.015467239527389903,
      "grad_norm": 0.15050296485424042,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5556,
      "step": 18
    },
    {
      "epoch": 0.017185821697099892,
      "eval_loss": 1.5292763710021973,
      "eval_runtime": 34.2687,
      "eval_samples_per_second": 14.299,
      "eval_steps_per_second": 7.149,
      "step": 20
    },
    {
      "epoch": 0.01804511278195489,
      "grad_norm": 0.14562292397022247,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.5016,
      "step": 21
    },
    {
      "epoch": 0.02062298603651987,
      "grad_norm": 0.15869614481925964,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.4865,
      "step": 24
    },
    {
      "epoch": 0.021482277121374866,
      "eval_loss": 1.5023248195648193,
      "eval_runtime": 34.5684,
      "eval_samples_per_second": 14.175,
      "eval_steps_per_second": 7.087,
      "step": 25
    },
    {
      "epoch": 0.023200859291084855,
      "grad_norm": 0.15873423218727112,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.5036,
      "step": 27
    },
    {
      "epoch": 0.02577873254564984,
      "grad_norm": 0.142244353890419,
      "learning_rate": 0.0,
      "loss": 1.52,
      "step": 30
    },
    {
      "epoch": 0.02577873254564984,
      "eval_loss": 1.4968665838241577,
      "eval_runtime": 34.2982,
      "eval_samples_per_second": 14.286,
      "eval_steps_per_second": 7.143,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3088106316103680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}